xuancoblab2023
commited on
Commit
•
932a897
1
Parent(s):
908c1a4
End of training
Browse files- README.md +72 -0
- model.safetensors +1 -1
README.md
ADDED
@@ -0,0 +1,72 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
base_model: google/bert_uncased_L-2_H-128_A-2
|
4 |
+
tags:
|
5 |
+
- generated_from_trainer
|
6 |
+
metrics:
|
7 |
+
- accuracy
|
8 |
+
model-index:
|
9 |
+
- name: Bert_tinybert-distilled
|
10 |
+
results: []
|
11 |
+
---
|
12 |
+
|
13 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
14 |
+
should probably proofread and complete it, then remove this comment. -->
|
15 |
+
|
16 |
+
# Bert_tinybert-distilled
|
17 |
+
|
18 |
+
This model is a fine-tuned version of [google/bert_uncased_L-2_H-128_A-2](https://huggingface.co/google/bert_uncased_L-2_H-128_A-2) on an unknown dataset.
|
19 |
+
It achieves the following results on the evaluation set:
|
20 |
+
- Loss: 0.4565
|
21 |
+
- Accuracy: 0.7973
|
22 |
+
- Auc: 0.8745
|
23 |
+
- Mcc: 0.6019
|
24 |
+
- Pr Auc: 0.8517
|
25 |
+
- Bac: 0.7973
|
26 |
+
|
27 |
+
## Model description
|
28 |
+
|
29 |
+
More information needed
|
30 |
+
|
31 |
+
## Intended uses & limitations
|
32 |
+
|
33 |
+
More information needed
|
34 |
+
|
35 |
+
## Training and evaluation data
|
36 |
+
|
37 |
+
More information needed
|
38 |
+
|
39 |
+
## Training procedure
|
40 |
+
|
41 |
+
### Training hyperparameters
|
42 |
+
|
43 |
+
The following hyperparameters were used during training:
|
44 |
+
- learning_rate: 0.0003098011180790181
|
45 |
+
- train_batch_size: 32
|
46 |
+
- eval_batch_size: 32
|
47 |
+
- seed: 33
|
48 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
49 |
+
- lr_scheduler_type: linear
|
50 |
+
- num_epochs: 9
|
51 |
+
|
52 |
+
### Training results
|
53 |
+
|
54 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Auc | Mcc | Pr Auc | Bac |
|
55 |
+
|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|:------:|:------:|:------:|
|
56 |
+
| 0.6039 | 1.0 | 172 | 0.5328 | 0.7033 | 0.8094 | 0.4152 | 0.7669 | 0.7033 |
|
57 |
+
| 0.5426 | 2.0 | 344 | 0.4892 | 0.78 | 0.8386 | 0.5777 | 0.7876 | 0.78 |
|
58 |
+
| 0.5225 | 3.0 | 516 | 0.4794 | 0.7847 | 0.8532 | 0.5774 | 0.8195 | 0.7847 |
|
59 |
+
| 0.5069 | 4.0 | 688 | 0.4593 | 0.7973 | 0.8656 | 0.5988 | 0.8310 | 0.7973 |
|
60 |
+
| 0.4971 | 5.0 | 860 | 0.4636 | 0.8 | 0.8696 | 0.6114 | 0.8421 | 0.8 |
|
61 |
+
| 0.479 | 6.0 | 1032 | 0.4567 | 0.802 | 0.8744 | 0.6146 | 0.8520 | 0.802 |
|
62 |
+
| 0.4733 | 7.0 | 1204 | 0.4559 | 0.8007 | 0.8706 | 0.6054 | 0.8510 | 0.8007 |
|
63 |
+
| 0.4647 | 8.0 | 1376 | 0.4525 | 0.8033 | 0.8733 | 0.6108 | 0.8499 | 0.8033 |
|
64 |
+
| 0.4646 | 9.0 | 1548 | 0.4565 | 0.7973 | 0.8745 | 0.6019 | 0.8517 | 0.7973 |
|
65 |
+
|
66 |
+
|
67 |
+
### Framework versions
|
68 |
+
|
69 |
+
- Transformers 4.43.2
|
70 |
+
- Pytorch 2.3.1+cu121
|
71 |
+
- Datasets 2.20.0
|
72 |
+
- Tokenizers 0.19.1
|
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 17549312
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b7e432a1d779e798d0c5935078bca6b85766dd7958077346e206106d710a20b0
|
3 |
size 17549312
|